6cdbc7a270
Show error for --continue mode, remove deleted code
2023-07-10 08:34:36 -07:00
a421aab7f0
Renamed template.execute() to template.evaluate() and added type hints
2023-07-10 08:27:28 -07:00
199f7e0767
Renamed iter_prompt() to execute() and updated tutorial
2023-07-10 07:59:12 -07:00
ae87f978bd
Moved iter_prompt from Response to Model, moved a lot of other stuff
...
- Moved a whole bunch of things from llm/cli.py into llm/__init__.py
- Switched plugin listings to use importlib.metadata to avoid deprecation warning
- iter_prompt() is now a method on Model, not on Response
2023-07-10 07:45:11 -07:00
902cf6010c
Fixed type hint on Prompt
2023-07-07 20:38:53 -07:00
3d5c9b2d3b
Read prompt after validating options
...
This means that if you do this:
llm -m markov -o length -1
You will see an error message rather than have the command hang
waiting for a prompt to be entered on stdin.
2023-07-06 19:57:04 -07:00
04568115b8
Options base class is now llm.Options not Model.Options
2023-07-05 20:47:36 -07:00
b4248df72a
Markov plugin now lives in llm-markov repo
2023-07-05 20:46:53 -07:00
4611bff412
iter_prompt() now takes prompt
2023-07-05 20:46:17 -07:00
c08344f986
llm logs now decodes JSON for prompt_json etc
2023-07-05 18:31:38 -07:00
b88906d459
Default __str__ method for models
2023-07-05 18:26:16 -07:00
6ef6b343a9
Improved how keys work, execute() now has default implementation
2023-07-05 18:25:57 -07:00
f193468f76
llm install -e/--editable option
2023-07-05 17:58:19 -07:00
78c93b9e23
Model.execute() model now defaults to using self.Response
2023-07-05 16:57:10 -07:00
23886e04ae
Better error message display
...
Refs https://github.com/pydantic/pydantic/issues/6441
2023-07-05 16:36:38 -07:00
bc8dad1e33
stream defaults to True on prompt() method
2023-07-04 08:14:00 -07:00
49e4d688c6
Removed .stream() method in favor of .prompt(stream=False)
2023-07-04 07:50:31 -07:00
3136948408
Moved things into inner classes, log_message is now defined on base Response
2023-07-03 21:25:19 -07:00
307af2474c
Fix column order in logs
2023-07-03 07:29:58 -07:00
345ad0d2dc
Implemented new logs database schema
2023-07-03 07:27:47 -07:00
b1c51df3f1
New LogMessage design, plus Response.json() method
2023-07-03 06:46:51 -07:00
61dd8afc60
Drop the debug field from the logs, combine chunks from stream
2023-07-03 06:39:54 -07:00
84b99f8baf
-o/--option, implemented for OpenAI models - closes #63
2023-07-02 17:42:22 -07:00
52add96ec1
Rough initial version of new logging, to log2 table
2023-07-02 16:35:36 -07:00
4a9f7f4908
Lint using Ruff, refs #78
2023-07-02 12:41:40 -07:00
3ed86e403d
Added mypy, plus some fixes to make it happy - refs #77
2023-07-02 12:36:22 -07:00
7054c673e1
Better type hint for iter_prompt method
...
The Generator thing is only useful if the method uses the send mechanism
Declaring it an Iterator gives people more flexibility for how they implement it.
2023-07-02 11:18:31 -07:00
9a180e65a8
llm models default command, plus refactored env variables
...
Closes #76
Closes #31
2023-07-01 14:01:29 -07:00
f3f38c0c02
Initial experimental response.reply() method
2023-07-01 13:29:54 -07:00
664fca165b
.stream is now in base Response class
2023-07-01 13:29:27 -07:00
183b647351
Removed PaLM 2 vertex model
...
It lives here now: https://github.com/simonw/llm-palm
Refs #20
2023-07-01 13:27:59 -07:00
feff460496
Fix for pydantic warning, refs #74
2023-07-01 11:56:35 -07:00
9ac120fae4
Upgrade to pydantic 2 using bump-pydantic, refs #74
2023-07-01 11:53:54 -07:00
9afc758cd7
Pass model to the Response
2023-07-01 11:29:41 -07:00
6ef52172b0
Fixed timezone related test failure
2023-07-01 11:14:25 -07:00
4d304d99e1
Fixed import error in llm openai models
2023-07-01 11:12:06 -07:00
1b3f14fe89
Move default plugins into llm/default_plugins
2023-07-01 11:10:30 -07:00
714b867e92
-s shortcut for --system, closes #69
2023-07-01 10:46:20 -07:00
c679d4d99e
llm openai models command, closes #70
2023-07-01 10:39:24 -07:00
c1938a4987
Fix for --key being beaten by env variable, closes #71
2023-07-01 10:33:49 -07:00
52cedc03e0
CLI now uses new prompt/stream methods
2023-07-01 09:09:19 -07:00
ffe4b6706d
Model.stream() and .get_key() methods
2023-07-01 09:03:07 -07:00
13fb4c2966
Refactor Template into templates.py
2023-07-01 08:27:45 -07:00
5e056fad8a
Implemented PaLM 2, to test out new plugin hook - refs #20
2023-06-26 08:25:01 -07:00
5103f77c40
New mechanism for handling API keys for models
2023-06-26 08:05:48 -07:00
274126d9f8
WIP register_models() plugin hook, refs #53
2023-06-26 07:43:46 -07:00
9f1085eece
--save now stores -p as default parameters, closes #58
2023-06-23 07:51:50 -07:00
059bc1a5fe
Handle error when no templates are found ( #47 )
...
Thanks, @sderev
2023-06-23 07:38:13 -07:00
97daa001aa
fix typo: 4-32k, not 4-16k ( #61 )
2023-06-23 07:37:09 -07:00
e72311982d
Added 4-16k shortcut
2023-06-21 07:45:22 +01:00
Simon Willison